ruygar/artha-ai-studio

Artha AI Studio — Models & Pre-Built Windows Wheels

This repository is the official hub for Artha AI Studio, hosting curated model weights, runtime assets, and pre-compiled Windows CUDA/C++ Python wheels (.whl) built for the portable Artha AI Studio environment.

---

Repository Structure

ruygar/artha-ai-studio/
├── wheels/                  # Pre-built Windows x64 CUDA Python wheels (.whl)
│   └── sage/                # SageAttention CUDA wheels (Ampere, Ada, Hopper, Blackwell)
└── models/                  # Studio-specific model weights and checkpoints

---

Pre-Built Windows Wheels (wheels/)

All wheels in this repository are compiled on Windows x64 using the portable Artha AI Studio build toolchain (MSVC 14.44 + CUDA 13.2).

1. SageAttention (wheels/sage/)

Wheel File	Version	CUDA	PyTorch	Python ABI	Supported GPU Architectures	Direct Link
sageattention-2.2.0+cu132torch2.13.0-cp310-abi3-win_amd64.whl	2.2.0	13.2	2.13.0+	cp310-abi3 (Python 3.10–3.13+)	sm_80, sm_86, sm_89, sm_90a, sm_120a (RTX 30xx / 40xx / 50xx)	Download

Key Features of This Build:

• Python Stable ABI (cp310-abi3) & LibTorch Stable ABI (TORCH_STABLE_ONLY): A single wheel works across Python 3.10, 3.11, 3.12, and 3.13+.
• Full RTX 5090 (sm_120) Support Across Both FP8 & FP16 Kernels: Includes native sm_89 and sm_120a + PTX binaries in both _qattn_sm89.pyd (sageattn_qk_int8_pv_fp8_cuda) and _qattn_sm80.pyd (sageattn_qk_int8_pv_fp16_cuda).

Direct Installation (pip):

pip install "https://huggingface.co/ruygar/artha-ai-studio/resolve/main/wheels/sage/sageattention-2.2.0%2Bcu132torch2.13.0-cp310-abi3-win_amd64.whl"

(Note: Requires triton-windows on Windows: pip install triton-windows)